© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 18767
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mueller" at varying levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual's name, particularly Robert Mueller

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ential
    -0.82
    compatible
    -0.80
     Pyr
    -0.75
    piring
    -0.75
    ----------------------------------------------------------------
    -0.74
    ---------
    -0.73
    Jonathan
    -0.70
    pipe
    -0.70
    Forward
    -0.69
    Template
    -0.68
    POSITIVE LOGITS
     Mueller
    1.37
    ueller
    1.05
    andowski
    1.01
     bund
    0.88
     lapt
    0.88
     dossier
    0.84
     indict
    0.81
    asonic
    0.79
    sonian
    0.79
    quist
    0.78
    Activations Density 0.007%

    No Known Activations